Update app.py

app.py

@@ -110,9 +110,6 @@ class SuperSmartAgent:
         final_state = self.graph.invoke(initial_state)
         return final_state["response"]
 
-
-    # --- HELPER METHODS (NOW PART OF THE CLASS) ---
-
     def score_text(self, text):
         alnum_count = sum(c.isalnum() for c in text)
         space_count = text.count(' ')
@@ -468,7 +465,6 @@ class SuperSmartAgent:
         cell = re.sub(r'\s+', ' ', cell).strip()
         return cell
 
-
     def extract_answer(self, question, context, tables=None):
         """
         Enhanced general purpose answer extraction from text context using spaCy.
@@ -729,7 +725,7 @@ class SuperSmartAgent:
         scored_numbers.sort(reverse=True, key=lambda x: x[0])
         return (scored_numbers[0][1], scored_numbers[0][2])
     
-        def find_relevant_location_spacy(self, question, entities):
+    def find_relevant_location_spacy(self, question, entities):
             """Find the most relevant location entity based on question context using spaCy."""
             location_entities = [ent for ent in entities if ent[1] in ["GPE", "LOC"]]
             if not location_entities:
@@ -763,80 +759,79 @@ class SuperSmartAgent:
                     best_location = loc_text
     
             return best_location
-    
-    
-        def find_answer_in_tables(self, question, tables):
-            """
-            Search through extracted tables to find an answer to the question.
-            Improved with better column type detection and keyword matching.
-            """
-            if not tables:
-                return None
-            
-            question_keywords = self.extract_key_phrases(question)
-            question_lower = question.lower()
-            
-            for table in tables:
-                if not table:
-                    continue
-    
-                # Assuming the first row is headers if present
-                headers = [self._clean_cell_content(cell).lower() for cell in table[0]] if table else []
-                data_rows = table[1:] if len(table) > 1 else []
-    
-                # Determine column types (placeholder for now, needs implementation)
-                column_types = self.detect_column_types(table)
-    
-                # ... (Rest of your table search logic would go here)
-                # For now, just return a dummy answer if a table is found to avoid the error.
-                # You'll need to implement the actual table search and answer extraction logic.
-                # Example:
-                if "president" in question_lower and "usa" in question_lower and headers and "name" in headers:
-                    name_col_idx = headers.index("name")
-                    # More complex logic needed to find relevant row
-                    return "Placeholder: Found answer in table for president question."
-                
-                # Simple keyword match within table cells as a basic example
-                for row_idx, row in enumerate(table):
-                    for cell_idx, cell_content in enumerate(row):
-                        cell_lower = cell_content.lower()
-                        if any(keyword in cell_lower for keyword in question_keywords):
-                            # This is very basic, a proper implementation would consider column headers
-                            # and question type to return a specific cell or a combination.
-                            if headers and cell_idx < len(headers):
-                                return f"Found '{cell_content}' under '{headers[cell_idx]}' in a table."
-                            else:
-                                return f"Found '{cell_content}' in a table."
+        
+    def find_answer_in_tables(self, question, tables):
+        """
+        Search through extracted tables to find an answer to the question.
+        Improved with better column type detection and keyword matching.
+        """
+        if not tables:
             return None
-    
-        def detect_column_types(self, table):
-            """
-            Detects the type of data in each column (e.g., 'number', 'text', 'date').
-            This is a placeholder and would need a robust implementation.
-            """
-            if not table or not table[0]:
-                return []
+        
+        question_keywords = self.extract_key_phrases(question)
+        question_lower = question.lower()
+        
+        for table in tables:
+            if not table:
+                continue
+
+            # Assuming the first row is headers if present
+            headers = [self._clean_cell_content(cell).lower() for cell in table[0]] if table else []
+            data_rows = table[1:] if len(table) > 1 else []
+
+            # Determine column types (placeholder for now, needs implementation)
+            column_types = self.detect_column_types(table)
+
+            # ... (Rest of your table search logic would go here)
+            # For now, just return a dummy answer if a table is found to avoid the error.
+            # You'll need to implement the actual table search and answer extraction logic.
+            # Example:
+            if "president" in question_lower and "usa" in question_lower and headers and "name" in headers:
+                name_col_idx = headers.index("name")
+                # More complex logic needed to find relevant row
+                return "Placeholder: Found answer in table for president question."
             
-            num_cols = len(table[0])
-            column_types = ["text"] * num_cols # Default to text
-    
-            # Example: rudimentary detection for the first few rows
-            for col_idx in range(num_cols):
-                num_count = 0
-                date_count = 0
-                for row_idx in range(1, min(len(table), 5)): # Check first 5 data rows
-                    if col_idx < len(table[row_idx]):
-                        cell_content = self._clean_cell_content(table[row_idx][col_idx])
-                        if re.match(r'^\d+(\.\d+)?$', cell_content):
-                            num_count += 1
-                        if re.match(r'\b\d{4}\b', cell_content) or re.match(r'\b(Jan|Feb|Mar)\w*\s+\d{1,2}(?:st|nd|rd|th)?(?:,\s+\d{4})?\b', cell_content, re.IGNORECASE):
-                            date_count += 1
-                
-                if num_count > 2: # Heuristic: if more than 2 numbers
-                    column_types[col_idx] = "number"
-                elif date_count > 1: # Heuristic: if more than 1 date
-                    column_types[col_idx] = "date"
-            return column_types
+            # Simple keyword match within table cells as a basic example
+            for row_idx, row in enumerate(table):
+                for cell_idx, cell_content in enumerate(row):
+                    cell_lower = cell_content.lower()
+                    if any(keyword in cell_lower for keyword in question_keywords):
+                        # This is very basic, a proper implementation would consider column headers
+                        # and question type to return a specific cell or a combination.
+                        if headers and cell_idx < len(headers):
+                            return f"Found '{cell_content}' under '{headers[cell_idx]}' in a table."
+                        else:
+                            return f"Found '{cell_content}' in a table."
+        return None
+
+    def detect_column_types(self, table):
+        """
+        Detects the type of data in each column (e.g., 'number', 'text', 'date').
+        This is a placeholder and would need a robust implementation.
+        """
+        if not table or not table[0]:
+            return []
+        
+        num_cols = len(table[0])
+        column_types = ["text"] * num_cols # Default to text
+
+        # Example: rudimentary detection for the first few rows
+        for col_idx in range(num_cols):
+            num_count = 0
+            date_count = 0
+            for row_idx in range(1, min(len(table), 5)): # Check first 5 data rows
+                if col_idx < len(table[row_idx]):
+                    cell_content = self._clean_cell_content(table[row_idx][col_idx])
+                    if re.match(r'^\d+(\.\d+)?$', cell_content):
+                        num_count += 1
+                    if re.match(r'\b\d{4}\b', cell_content) or re.match(r'\b(Jan|Feb|Mar)\w*\s+\d{1,2}(?:st|nd|rd|th)?(?:,\s+\d{4})?\b', cell_content, re.IGNORECASE):
+                        date_count += 1
+            
+            if num_count > 2: # Heuristic: if more than 2 numbers
+                column_types[col_idx] = "number"
+            elif date_count > 1: # Heuristic: if more than 1 date
+                column_types[col_idx] = "date"
+        return column_types
 
 # --- Gradio Interface (as provided, assuming it will call agent correctly) ---